Sekretaerbaer-Netz/Blocked_Bots_and_Crawler_Sekretaerbaer.de
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'refs/heads/develop'

Browse source 
update ai.robots.txt
add robots.txt
add apache-badbots.conf
This commit is contained in:
oldkid 2025-04-26 06:58:32 +02:00
commit 2bb3d4c9c9
5 changed files with 89 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
apache-badbots.conf Normal file
View file

@ -0,0 +1 @@
I2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google\-Extended|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|imgproxy|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity\-User|PerplexityBot|PetalBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot|AhrefsBot|Baiduspider|Barkrowler|Bingbot|BLEXBot|Bytedance|DotBot|EmailCollector|facebookcatalog|facebookexternalhit|fidget-spinner-bot|Franck the Fediverse Graph Crawler|Googlebot|Livelapbot|Mediapartners-Google|MJ12bot|SemrushBot|SeznamBot|VelenPublicWebCrawler|WebEMailExtrac|YandexBot|YisouSpider|

80
robots.txt Normal file
View file

@ -0,0 +1,80 @@
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: aiHitBot
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Brightbot 1.0
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Cotoyogi
User-agent: Crawlspace
User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: FacebookBot
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
User-agent: FriendlyCrawler
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: GPTBot
User-agent: iaskspider/2.0
User-agent: ICC-Crawler
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: imgproxy
User-agent: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
User-agent: meta-externalagent
User-agent: Meta-ExternalAgent
User-agent: meta-externalfetcher
User-agent: Meta-ExternalFetcher
User-agent: NovaAct
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: omgilibot
User-agent: Operator
User-agent: PanguBot
User-agent: Perplexity-User
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: Scrapy
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SWA
User-agent: Sidetrade indexer bot
User-agent: TikTokSpider
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: YouBot
User-agent: AhrefsBot
User-agent: Baiduspider
User-agent: Barkrowler
User-agent: Bingbot
User-agent: BLEXBot
User-agent: Bytedance
User-agent: DotBot
User-agent: EmailCollector
User-agent: facebookcatalog
User-agent: facebookexternalhit
User-agent: fidget-spinner-bot
User-agent: Franck the Fediverse Graph Crawler
User-agent: Googlebot
User-agent: Livelapbot
User-agent: Mediapartners-Google
User-agent: MJ12bot
User-agent: SemrushBot
User-agent: SeznamBot
User-agent: VelenPublicWebCrawler
User-agent: WebEMailExtrac
User-agent: YandexBot
User-agent: YisouSpider
Disallow: /

3
source/ai.robots.txt /.htaccess Normal file
View file

@ -0,0 +1,3 @@
RewriteEngine On
RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google\-Extended|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|imgproxy|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity\-User|PerplexityBot|PetalBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot) [NC]
RewriteRule !^/?robots\.txt$ - [F,L]

3
source/ai.robots.txt /nginx-block-ai-bots.conf Normal file
View file

@ -0,0 +1,3 @@
if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google\-Extended|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|imgproxy|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity\-User|PerplexityBot|PetalBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot)") {
return 403;
}

2
source/ai.robots.txt /robots.txt
View file

@ -34,7 +34,9 @@ User-agent: imgproxy
User-agent: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
User-agent: meta-externalagent
User-agent: Meta-ExternalAgent
User-agent: meta-externalfetcher
User-agent: Meta-ExternalFetcher
User-agent: NovaAct
User-agent: OAI-SearchBot
User-agent: omgili